@deccancollege.ac.in
Professor of Civil Engineering & Director of Technical Campus
Deccan College of Engineering and Technology
Academic Administration & Leadership, Faculty/Researcher - Civil Engineering and Consultant – ADR (Arbitrator & Mediator), PQP & QA/QC, Lead Auditor - ISO 9001:2015, promoting technology to the world for the benefit of the society.
Ph.D (Civil Engineering), MBA (HR)
Civil and Structural Engineering, Building and Construction, Geotechnical Engineering and Engineering Geology, Management Science and Operations Research
Scopus Publications
Humera Khanum, Anshul Garg, and Mir Iqbal Faheem
F1000 Research Ltd
Background: Road accidents claim around 1.35 million lives annually, with countries like India facing a significant impact. In 2019, India reported 449,002 road accidents, causing 151,113 deaths and 451,361 injuries. Accident severity modeling helps understand contributing factors and develop preventive strategies. AI models, such as random forest, offer adaptability and higher predictive accuracy compared to traditional statistical models. This study aims to develop a predictive model for traffic accident severity on Indian highways using the random forest algorithm. Methods: A multi-step methodology was employed, involving data collection and preparation, feature selection, training a random forest model, tuning parameters, and evaluating the model using accuracy and F1 score. Data sources included MoRTH and NHAI. Results: The classification model had hyperparameters ‘max depth’: 10, ‘max features’: ‘sqrt’, and ‘n estimators’: 100. The model achieved an overall accuracy of 67% and a weighted average F1-score of 0.64 on the training set, with a macro average F1-score of 0.53. Using grid search, a random forest Classifier was fitted with optimal parameters, resulting in 41.47% accuracy on test data. Conclusions: The random forest classifier model predicted traffic accident severity with 67% accuracy on the training set and 41.47% on the test set, suggesting possible bias or imbalance in the dataset. No clear patterns were found between the day of the week and accident occurrence or severity. Performance can be improved by addressing dataset imbalance and refining model hyperparameters. The model often underestimated accident severity, highlighting the influence of external factors. Adopting a sophisticated data recording system in line with MoRTH and IRC guidelines and integrating machine learning techniques can enhance road safety modeling, decision-making, and accident prevention efforts.
Mohammed Abdul Wajid Siddiqui and Mir Iqbal Faheem
Springer International Publishing
Sajad Ahmad Wani, Aejaz Ahsan Baba, Gowhar Nazir Mufti, Kumar Abdul Rashid, Nisar Ahmad Bhat, Mudasir Buch, and Mir Faheem
Springer Science and Business Media LLC
V. S. S. Kumar and Mir Iqbal Faheem
American Society of Civil Engineers
2 Abstract: Present day construction and in its associated activities is an involved process due to the phenomenal increase in various facets of constructional activities. The complexity of the decision parameters adds new dimension in the decision making process for technology transfer. Thus, the need to rationalize the various inputs and optimize the construction planning practices becomes imperative. Several considerations that are qualitatively described by the terms such as high, medium, low, good, bad and satisfactory have an important bearing on the engineering aspects of projects and the structures therein. The subjective judgments implicit in these qualitative terms cannot be directly incorporated into the analysis and planning of engineering activities in a routine way through classical evaluation. The fuzzy set theory makes available a convenient and meaningful tool to the practising engineers to incorporate these seemingly vague but practically powerful factors in the several phases of a project life cycle. This paper reports a methodology for incorporating the fuzzy set concept into the procedural analysis of planning the buildings in challenging environments with or without proper weightages assigned for the qualitative factors. Intangible, non-quantitative and linguistic variables are considered for the evaluation process relatively in an easier way through this concept.